News for hackers. Stuff that matters.
Re:Show HN: I have created a free text-to-image website that... by webmaven on Sunday December 17, 2023 @10:14AM (#38673369)
Nice! What settings are you using (steps, etc.)?
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by frankmao on Sunday December 17, 2023 @11:06AM (#38673754)
It's SDXL turbo model. And it only has 1 step.
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by webmaven on Sunday December 17, 2023 @04:16PM (#38676530)
Okay, and the other settings? Guidance, sampler, etc?
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by velcrovan on Sunday December 17, 2023 @10:56AM (#38673663)
Consider adding a spinner and disabling the generate button once clicked, otherwise there's no indication that clicking the button did anything.

The generated faces are whack

[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by frankmao on Sunday December 17, 2023 @11:09AM (#38673778)
There is spinner on the PC side. You can generate face using https://comfyuiweb.com/Pixart-alpha. The model is perfect and can generate 1024x1024 resolution images.
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by neontomo on Sunday December 17, 2023 @11:33AM (#38673934)
I also did not see any spinner on the PC side, but cool project and I love how fast it is.
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by noman-land on Sunday December 17, 2023 @11:07AM (#38673758)
How are you able to provide this service for free? What if someone generates tens of thousands of images? Won't that be very expensive for you?
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by frankmao on Sunday December 17, 2023 @11:12AM (#38673790)
Yes, there is a certain queue for the free service. If too much is generated, the longer the wait time is. The SDXL Turbo model has a manageable cost because it is generated faster.
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by ilaksh on Sunday December 17, 2023 @11:41AM (#38674013)
I assume your plan is to just hope that Stability.AI doesn't bother using you? Clearly this is a commercial service.
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by frankmao on Sunday December 17, 2023 @12:13PM (#38674353)
Yeah, I know. I'm not doing anything profitable with the model, but of course if I wanted to commercialize it, I'd apply for a license from stability.ai
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by simonw on Sunday December 17, 2023 @11:51AM (#38674149)
https://github.com/Stability-AI/generative-models/blob/main/... doesn't have any restrictions on commercial usage does it?
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by out_of_protocol on Sunday December 17, 2023 @11:58AM (#38674215)
SDXL != SDXL-turbo, different license
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by simonw on Sunday December 17, 2023 @03:42PM (#38676211)
https://huggingface.co/stabilityai/sdxl-turbo/blob/main/LICE...

Huh, TIL: "STABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT"

[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by frankmao on Sunday December 17, 2023 @07:41PM (#38677963)
I learned. I will be replacing the model soon. I haven't looked too closely at the license.
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by bsenftner on Sunday December 17, 2023 @11:50AM (#38674129)
One would think, being described as "Comfyui Online" the expectation is the Comfy UI itself. Since it is not, is this not a misappropriation of the Comfy UI team's identity and their own grass root branding?
[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by brucethemoose2 on Sunday December 17, 2023 @11:54AM (#38674173)
Yeah, I am on the fence about flagging this post actually. Using the branding so blatantly feels really slimey.

That would be bad HN etiquette, right? Its not a straight up scam, its seemingly a legitimate service...

[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by cmdr2 on Sunday December 17, 2023 @12:51PM (#38674720)
Yeah, I assumed it was made by Comfy's author, as maybe a next evolution of their project. I was feeling happy for them.

But since it's not made by Comfy's author, it's definitely not cool to name your project by using their name.

[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by brucethemoose2 on Sunday December 17, 2023 @11:58AM (#38674212)
Also see artbot, an actually free SD image generator: https://tinybots.net/artbot

The front end is all in the web app, and the backend generation is done by a swarm of volunteer hosts running on the AI Horde. I donate GPU time on my own 3090/2060 sometimes (albeit for text generation, not imagegen).

https://aihorde.net/

The whole thing is an awesome and tragically underused system.

[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by alsuren on Sunday December 17, 2023 @06:04PM (#38677315)
This is a pretty cool idea.

Recently I have been using SD 1.5 checkpoints with the LCM lora for all of my image generation (generally weighted down to 0.8 strength, with 6 step inference). It's not as fast as sdxl turbo, but at least it does a good job of people's faces.

It would be good to make more efficient use of people's donated resources by making it possible to use LCM lora.

[ Parent | on HN ]
Re:Show HN: I have created a free text-to-image website that... by smusamashah on Sunday December 17, 2023 @12:30PM (#38674527)
Why you named it ComfyUI? Your name make it sound like you are making that whole interface available online while infact you are only using that as your backend.
[ Parent | on HN ]